Can the RTX 3080 Ti run Mistral-7B-Instruct-v0.2?
Yes. Mistral-7B-Instruct-v0.2 fits the RTX 3080 Ti's 12 GB at Q4_K_M (about 5.8 GB needed), running at an estimated 131 tok/s. There's room for up to Q8_0 if you want higher quality.
Every quantization
Mistral-7B-Instruct-v0.2 (7.2B) on 12 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 4 GB | 5.8 GB | Fits easily | ~131 tok/s |
| Q5_K_M | 5 GB | 6.8 GB | Fits easily | ~105 tok/s |
| Q8_0 | 8 GB | 9.8 GB | Fits | ~65 tok/s |
| FP16 | 14 GB | 15.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 3080 Ti's 912 GB/s bandwidth (XiongjieDai/GPU-Benchmarks-on-LLM-Inference). Long contexts need more memory and run slower.
Run it
Copy, paste, go
llama-server -hf TheBloke/Mistral-7B-Instruct-v0.2-GGUF -ngl 99Ollama pulls a Q4 build by default. Pick a larger quant only if the table above says it fits. Full Mistral-7B-Instruct-v0.2 details →
Compare
Same model, other hardware - and other models on this card
Mistral-7B-Instruct-v0.2 on other hardware
- RTX 5090~257 tok/s
- RTX 5090 D~257 tok/s
- RTX 6000D~225 tok/s
- RTX 4090~156 tok/s
- Radeon RX 7900 XTX~138 tok/s
- RTX 5080~138 tok/s
- RTX 3090~137 tok/s
- RTX 5080 Mobile~129 tok/s
Also runs on the RTX 3080 Ti
- Qwen3 14B~65 tok/s
- Gemma 4 12B~75 tok/s
- Qwen3.5 9B~87 tok/s
- Llama 3.1 8B~95 tok/s
- Qwen3.5 4B~174 tok/s
- Qwen3-4B-Instruct-2507~261 tok/s
- NVIDIA Nemotron 3 Nano 4B~261 tok/s
- Phi-4 Mini~209 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX 3080 Ti run Mistral-7B-Instruct-v0.2?
Yes. Mistral-7B-Instruct-v0.2 fits the RTX 3080 Ti's 12 GB at Q4_K_M (about 5.8 GB needed), running at an estimated 131 tok/s. There's room for up to Q8_0 if you want higher quality.
How much VRAM does Mistral-7B-Instruct-v0.2 need?
About 4 GB of weights at Q4_K_M, 8 GB at Q8_0 and 14 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is Mistral-7B-Instruct-v0.2 on the RTX 3080 Ti?
Roughly 131 tokens per second at Q4_K_M (single user, llama.cpp-style decode). This is an estimate from the RTX 3080 Ti's 912 GB/s memory bandwidth.